# Token Limits when adding in info

**URL:** <https://community.pickaxe.co/t/token-limits-when-adding-in-info/2577>\
**Category:** General\
**Created:** [November 15, 2024, 6:54pm UTC](https://community.pickaxe.co/t/token-limits-when-adding-in-info/2577 "2024-11-15T18:54:53Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![ihmunro](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/ihmunro/32/592_2.png) [@ihmunro](https://community.pickaxe.co/u/ihmunro)\
**Post date:** [November 15, 2024, 6:54pm UTC](https://community.pickaxe.co/t/token-limits-when-adding-in-info/2577/1 "2024-11-15T18:54:53Z")

</div>

I just came across an instance where I was trying to get aa bunch of info back based upon an input.

I got an error saying that the input was to large and exceeded the tokens.

Is there somewhere that this can be adjusted up ?

---

<div class="post-metadata">

**Author:** ![ab2308](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/ab2308/32/1542_2.png) [@ab2308](https://community.pickaxe.co/u/ab2308)\
**Post date:** [November 16, 2024, 4:25am UTC](https://community.pickaxe.co/t/token-limits-when-adding-in-info/2577/2 "2024-11-16T04:25:21Z")

</div>

@ihmunro you can adjust the token input / output length in the configure tab of the pickaxe.

Having said that be aware of the underlying model context limit. GPT-4-turbo and GPT-4o have a context length of 128k

---

<div class="post-metadata">

**Author:** ![ihmunro](https://yyz2.discourse-cdn.com/flex004/user_avatar/community.pickaxe.co/ihmunro/32/592_2.png) [@ihmunro](https://community.pickaxe.co/u/ihmunro)\
**Post date:** [November 16, 2024, 7:32pm UTC](https://community.pickaxe.co/t/token-limits-when-adding-in-info/2577/3 "2024-11-16T19:32:18Z")

</div>

thanks AB

Will take a look
